f5cd27b71d
server: streaming of tool calls and thoughts when --jinja is on (#12379 )
...
* add common_json w/ support for truncated json healing
* add common_chat_msg_diff
* partial common_chat_parse
* refactor parser w/ optionals
* server: wire chat diffs in stream mode
* fix trigger of thinking models (must happen after thoughts are closed)
* fix functionary v3.2 raw python!
* rename: common_chat_syntax (now contains format)
* rm common_regex.at_start
* don't return empty <think></think>
* accommodate yet another deepseek r1 distill fantasy syntax (`<｜tool▁calls｜>`)
* fix QwQ 32B tool call parsing after thoughts (hermes2)
* better logs for grammar triggers
* consume spaces after parse_json_tool_calls
* fix required tool calls w/ thinking models that have pre-opened thinking tags
* fix thinking model's initial trigger + test qwq's template
* run most test_tool_call tests in stream + non-stream modes
* make functionary v3.2 parsing more strict (differentiate first match from others)
* send final diff from server, to close off raw python arguments
* support partial content streaming in Generic mode
* tool-call: allow content prelude before hermes2 tool calls (for Qwen2.5)
* Update function-calling.md
* Update tool_bench.py
* chat-parser: remove input from exception (llm output may contain PII)
---------
Co-authored-by: ochafik <ochafik@google.com >
Co-authored-by: Olivier Chafik <ochafik@users.noreply.github.com >
2025-05-25 01:48:08 +01:00
a2d02d5793
releases : bundle llvm omp library in windows release ( #13763 )
2025-05-25 00:55:16 +02:00
17fc817b58
releases : enable openmp in windows cpu backend build ( #13756 )
2025-05-24 22:27:03 +02:00
2bd1b30f69
ggml-cpu : set openmp wait time if not set ( #13758 )
2025-05-24 22:26:47 +02:00
259469c4b5
Move GLM4 f32 attention fix to the correct function ( #13750 )
2025-05-24 16:49:12 +02:00
4c32832c59
ggml : add ggml_gelu_erf() CUDA kernel ( #13719 )
...
* ggml : add ggml_gelu_erf() CUDA kernel
* missing semicolon
2025-05-24 13:06:47 +02:00
c3a2624339
vocab : fix ugm tokenizer precision ( #13743 )
2025-05-24 12:29:09 +02:00
ffd0eae60b
CUDA: fix race condition in FA vector kernels ( #13742 )
2025-05-24 11:46:19 +02:00
b775345d78
ci : enable winget package updates ( #13734 )
2025-05-23 23:14:00 +03:00
a70a8a69c2
ci : add winget package updater ( #13732 )
2025-05-23 22:09:38 +02:00
d13d0f6135
hparams : initialize arrays ( #13728 )
...
ggml-ci
2025-05-23 20:16:13 +03:00
8a2afb7520
llama : allow custom list of swa_layers ( #13726 )
2025-05-23 17:07:04 +02:00
9ecf3e66a3
server : support audio input ( #13714 )
...
* server : support audio input
* add audio support on webui
2025-05-23 11:03:47 +02:00
faaaff5f94
CANN: Support MUL_MAT_ID for q8_0 and q4_0 ( #13705 )
...
* [CANN]Support MUL_MAT_ID Q8 && Q4
Signed-off-by: noemotiovon <757486878@qq.com >
* codestyle adjustment
Signed-off-by: noemotiovon <757486878@qq.com >
---------
Signed-off-by: noemotiovon <757486878@qq.com >
2025-05-23 16:47:53 +08:00
e16c4731c7
ggml : fix the order of ggml_unary_op ( #13718 )
2025-05-23 08:12:48 +02:00
1dcd01960c
vulkan: support CPY from any type to itself ( #13695 )
...
Reuse the f16/f32 copy shaders, and just scale the number of elements
according to the type size.
2025-05-23 06:45:02 +02:00
c10ed6cbcc
vulkan: Disable coopmat/coopmat2/bfloat extensions if glslc doesn't support it ( #13696 )
2025-05-23 06:33:45 +02:00
a127ff1780
use LOG_WARN to replace std::cerr ( #13657 )
2025-05-23 06:33:08 +02:00
3079e9ac8e
release : fix windows hip release ( #13707 )
...
* release : fix windows hip release
* make single hip release with multiple targets
2025-05-23 00:21:37 +02:00
8a1d206f1d
tts : fix n_ubatch + make WavTokenizer cache-less ( #13713 )
...
ggml-ci
2025-05-22 22:21:07 +03:00
797990c4bc
mtmd : add ultravox audio input ( #13623 )
...
* convert ok, load ok
* warmup ok
* test
* still does not work?
* fix padding
* temporary give up
* fix merge conflict
* build_ultravox()
* rm test
* fix merge conflict
* add necessary mtmd APIs
* first working version (only 4s of audio)
* will this monster compile?
* fix compile
* please compile
* fPIC
* fix windows
* various fixes
* clean up audio_helpers
* fix conversion
* add some debug stuff
* long audio input ok
* adapt the api
* add --audio arg
* final touch UX
* add miniaudio to readme
* fix typo
* refactor kv metadata
* mtmd_default_marker()
2025-05-22 20:42:48 +02:00
ab86335760
common: Include torch package for s390x ( #13699 )
...
* common: update requirements.txt to include pytorch nightly for s390x
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com >
* common: fix torch installation via pip for s390x
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com >
---------
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com >
2025-05-22 21:31:29 +03:00
cc74d5be99
server : pad small embedding batches ( #13692 )
...
ggml-ci
2025-05-22 16:33:39 +03:00
5be24af73d
gguf-py : correct charsmap parameter typing ( #13701 )
2025-05-22 14:25:05 +02:00
d394a9aedc
sycl : Remove waits from function calls ( #13702 )
...
* removes the waits in async memcpy functions
2025-05-22 12:54:43 +01:00
6b56a64690
SYCL: Avoid using with SYCL-Graph for unsupported nodes ( #13587 )
...
Currently on a CUDA backend to SYCL when running
`GGML_SYCL_DISABLE_GRAPH=0 ./bin/test-backend-ops -b SYCL0` there
are two operations that throw an exception from the blocking
waits during queue recording.
* `-o CONCAT` : Use of blocking waits on a queue that's being recorded https://github.com/ggml-org/llama.cpp/blob/master/ggml/src/ggml-sycl/concat.cpp#L185-L187
* `-o MUL_MAT_ID`: Blocking wait on a recording queue for a copy to host memory https://github.com/ggml-org/llama.cpp/blob/master/ggml/src/ggml-sycl/ggml-sycl.cpp#L3072-L3074
We've noticed that `ggml-cuda.cu` has the
[check_node_graph_compatibility_and_refresh_copy_ops](39e73ae0d6/ggml/src/ggml-cuda/ggml-cuda.cu (L2458-L2458)
2025-05-22 16:24:09 +08:00
a4e8912dfd
opencl: Add support for multiple devices ( #12622 )
...
* opencl: Add support for multiple devices
... but limited to one platform. A platform with a GPU will be preferred.
Additionally:
* Filter out devices that lack capabilities needed by the backend
implementation (half support, OpenCL 2.0+, etc).
* Make ggml_backend_opencl_reg() thread-safe.
* fixup: fix an error in sync_with_other_backends
... when there is only one OpenCL device available.
2025-05-21 16:21:45 -07:00
edbf42edfd
opencl: fix couple crashes ( #12795 )
...
* opencl: fix couple crashes
* fix kernel launches failed on devices which do not support
non-uniform work-groups. When non-uniform work-groups are not
supported, set `local_work_size` to NULL (= let driver choose the
work-group sizes). This patch does not cover everything - just the
cases tested by test-backend-ops.
* fix sub-buffer creation failed due to `cl_buffer_region::origin` not
being aligned to `CL_DEVICE_MEM_BASE_ADDR_ALIGN`.
* OpenCL: query non-uniform WG sizes only on OpenCL 3.0+
2025-05-21 13:21:17 -07:00
d643bb2c79
releases : build CPU backend separately (windows) ( #13642 )
2025-05-21 22:09:57 +02:00
8e186ef0e7
hparams : support models for which all layers use SWA ( #13682 )
...
ggml-ci
2025-05-21 20:00:49 +03:00
5fbfe384d4
server : improve error reporting ( #13680 )
2025-05-21 19:46:56 +03:00
c76532e7ba
convert : add qwen2vl support for unsloth merges ( #13686 )
2025-05-21 18:40:35 +02:00
2aa777d86d
examples : switch retrieval to llama_encode ( #13685 )
...
* switch retrieval to llama_encode
* enable --no-warmup for retrieval
2025-05-21 16:57:38 +02:00
eb0f5c28d3
gguf-py : display the invalid gguf type ( #13687 )
...
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com >
2025-05-21 16:33:54 +02:00
cf4cb59e64
ggml : add ggml_gelu_erf() ( #13667 )
...
* ggml : add ggml_gelu_na (not approximated)
* fix naming order
* rename na --> erf
* apply review suggesions
* revert naming order
2025-05-21 16:26:33 +02:00
0d5c742161
server : Add the endpoints /api/tags and /api/chat ( #13659 )
...
* Add the endpoints /api/tags and /api/chat
Add the endpoints /api/tags and /api/chat, and improved the model metadata response
* Remove trailing whitespaces
* Removed code that is not needed for copilot to work.
2025-05-21 15:15:27 +02:00
42158ae2e8
server : fix first message identification ( #13634 )
...
* server : fix first message identification
When using the OpenAI SDK (https://github.com/openai/openai-node/blob/master/src/lib/ChatCompletionStream.ts#L623-L626 ) we noticed that the expected assistant role is missing in the first streaming message. Fix this by correctly checking for the first message.
Co-authored-by: Piotr Stankiewicz <piotr.stankiewicz@docker.com >
Signed-off-by: Dorin Geman <dorin.geman@docker.com >
* server : Fix checks for first role message for stream=True
Co-authored-by: Piotr Stankiewicz <piotr.stankiewicz@docker.com >
Signed-off-by: Dorin Geman <dorin.geman@docker.com >
---------
Signed-off-by: Dorin Geman <dorin.geman@docker.com >
Co-authored-by: Piotr Stankiewicz <piotr.stankiewicz@docker.com >
2025-05-21 15:07:57 +02:00
797f2ac062
kv-cache : simplify the interface ( #13660 )
...
* kv-cache : simplify the interface
ggml-ci
* context : revert llama_batch_allocr position change
ggml-ci
2025-05-21 15:11:13 +03:00
b44890df2e
model : disable SWA for Phi models ( #13676 )
...
* model : disable SWA for Phi models
ggml-ci
* model : update warning message
* model : print warning only if n_swa > 0
* model : fix typo
2025-05-21 13:09:21 +03:00
33983057d0
musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy ( #13647 )
...
* musa: fix build warning (unused parameter)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com >
* musa: upgrade MUSA SDK version to rc4.0.1
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com >
* musa: use mudnn::Unary::IDENTITY op to accelerate D2D memory copy
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com >
* Update ggml/src/ggml-cuda/cpy.cu
Co-authored-by: Johannes Gäßler <johannesg@5d6.de >
* musa: remove MUDNN_CHECK_GEN and use CUDA_CHECK_GEN instead in MUDNN_CHECK
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com >
---------
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com >
Co-authored-by: Johannes Gäßler <johannesg@5d6.de >
2025-05-21 09:58:49 +08:00
fb1cab201c
vulkan: fix warnings ( #13626 )
...
* small fixes
* remove ifdef
2025-05-20 21:35:16 +00:00
b7a17463ec
mtmd-helper : bug fix to token batching in mtmd ( #13650 )
...
* Update mtmd-helper.cpp
* Update tools/mtmd/mtmd-helper.cpp
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com >
---------
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com >
2025-05-20 18:55:30 +02:00
be0239693c
model : fix llama4 graph ( #13663 )
...
ggml-ci
2025-05-20 19:21:04 +03:00
a4090d1174
llama : remove llama_kv_cache_view API + remove deprecated ( #13653 )
...
ggml-ci
2025-05-20 16:13:16 +03:00
b69f1647f9
CUDA: skip fully masked-out KV in FA vec kernel ( #13584 )
...
* CUDA: skip fully masked-out KV in FA vec kernel
2025-05-20 14:45:07 +02:00
759e37b0d8
tests : avoid github urls due to throttling ( #13654 )
2025-05-20 12:03:17 +02:00
4245e622e0
sycl: disable reorder for sycl mulmat ( #13536 )
2025-05-20 11:34:15 +02:00
c9c64dee57
Set GLM4 blk.*.attn_output.weight, kqv_out-* matmul to GGML_PREC_F32 to fix infinity values in output ( #13639 )
2025-05-20 10:11:56 +02:00
c00a2634be
metal : fix typo in FA kernel comments ( #13651 )
2025-05-20 10:41:40 +03:00
e298d2fbd0
kv-cache : add SWA support ( #13194 )
...
* kv-cache : prepare for SWA
ggml-ci
* kv-cache : initial iSWA implementation
ggml-ci
* kv-cache : rework error recovery logic
ggml-ci
* models : fix Phi-3 SWA parameters
ggml-ci
* model : adjust Granite to rope factor changes
ggml-ci
* server : check if context can do shifts
ggml-ci
* iswa : for now, always enable shifts (experiment)
ggml-ci
* kv-cache : simplify SWA logic
ggml-ci
* kv-cache : apply defrag when we fail to find slots for the batch
ggml-ci
* llama : update docs about llama_decode
ggml-ci
* kv-cache : update warning logs when no space for the batch is available
ggml-ci
* llama : add llama_kv_self_seq_pos_min()
* kv-cache : keep track of partial SWA computes and print warnings
* server : disallow use cases involving partial SWA context
ggml-ci
* llama : add param to control SWA cache size
ggml-ci
* minor : clean-up
ggml-ci
2025-05-20 08:05:46 +03:00
